metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- rouge
- precision
- recall
- f1
model-index:
- name: LLM_Teached_Bart_From_Scratch
results: []
LLM_Teached_Bart_From_Scratch
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4999
- Rouge1: 0.4331
- Rouge2: 0.2164
- Rougel: 0.3724
- Rougelsum: 0.3725
- Gen Len: 19.9255
- Precision: 0.9125
- Recall: 0.8885
- F1: 0.9002
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 390 | 1.5709 | 0.4119 | 0.2002 | 0.3529 | 0.3527 | 19.9709 | 0.9093 | 0.8846 | 0.8966 |
| 1.8155 | 2.0 | 781 | 1.5361 | 0.4331 | 0.2157 | 0.3717 | 0.3717 | 19.9185 | 0.9123 | 0.8889 | 0.9003 |
| 1.5875 | 3.0 | 1172 | 1.5030 | 0.4263 | 0.2129 | 0.3671 | 0.3673 | 19.9545 | 0.9117 | 0.8871 | 0.899 |
| 1.4978 | 3.99 | 1560 | 1.4999 | 0.4331 | 0.2164 | 0.3724 | 0.3725 | 19.9255 | 0.9125 | 0.8885 | 0.9002 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.15.0